LEOPARD project first identified a set of variables with potential predictive value that will serve as the foundation for training advanced first-generation AI-based predictive models. These include both routinely collected data from national OSO systems and a set of additional, clinically relevant variables selected by expert clinicians. Two tailored datasets were created: one for patients with DC and other end-stage liver diseases, and another for patients with HCC in order to obtain clinical predictors relevant to each patient population.
A major milestone was the launch of the Training and Validation Data Collection Study (TVDCS – NCT06675604). This prospective, multicenter European study includes two sub-cohorts:
• A training cohort used to develop second-generation predictive models.
• A validation cohort used to test the performance of these models under real-world conditions.
Between February and June 2025, data were collected from patients across five countries (France, Italy, Germany, Belgium, and Austria), with 22 centers active and >120 patients already enrolled. Study launch in Spain and the Netherlands is expected by September 2025 to enroll patients from 65 transplant centres in 7 countries.
In parallel, a second clinical study, PVC1 (NCT06723275) has been prepared. This study provides an independent external validation of the LEOPARD models while supporting the integration of cutting-edge omics and radiomics data to shape the development of third-generation models. The clinical protocol and all regulatory documentation have been finalized. Ethics submission has been completed in France and is scheduled for September in the remaining participating countries. Dedicated electronic Case Report Forms (eCRFs) and harmonized data infrastructure are already in place.
To ensure secure and consistent data collection across all LEOPARD activities, a pseudonymized identifier system has been developed, allowing tracking of patient data without storing any personally identifiable information. All data flows, are securely encrypted and managed. Access is restricted and monitored through rigorous audit mechanisms.
The project also established a dedicated LEOPARD Imaging Repository, designed to centralize and harmonize imaging data collected from participating centers.
From an operational perspective, LEOPARD has achieved solid governance and coordination:
• A Scientific Advisory Board was set up, providing strategic insight and enhancing scientific direction.
• A strong coordination structure has supported effective collaboration across partners and work packages.
• Key milestones have been reached, and core deliverables were submitted on time, reflecting successful project implementation.
In line with its commitment to equity and inclusion, the project launched a Gender and Diversity Monitoring Framework. This initiative tracks relevant indicators and promotes inclusive participation in all project activities.
Overall, LEOPARD has laid a robust foundation for its scientific and technological goals. It has successfully initiated a major study, developed key digital infrastructures, and ensured regulatory preparednress for the launch of the second study. The work conducted to date sets the stage for upcoming breakthroughs in AI-driven liver transplant prioritization, with the potential to impact clinical practice and health policy across Europe.
